claude-code-deepseek-delegator@3.0.1
CAUTIONPublisher claims: "MCP server that lets Claude Code delegate heavy-token tasks to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Claude orchestrates; the delegate does the heavy lifting. Zero dependencies." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-30 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessexec /usr/bin/timeout
0.1sclaimed4 tools: delegate, delegate_models, deepseek, deepseek_models
0.1sprocessscript backend runs setup only
Static findings
MEDIUM
npx invocation of non-well-known packagesrc/setup/init.mjs:619 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/setup/doctor.mjs:88 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/index.mjs:142 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06HIGH
Access to sensitive file pathspackage.json:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
npx invocation of non-well-known packagesrc/index.mjs:180 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06HIGH
Access to sensitive file pathssrc/setup/init.mjs:523 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05HIGH
Access to sensitive file pathssrc/providers/registry.mjs:73 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
npx invocation of non-well-known packagesrc/setup/init.mjs:490 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/setup/doctor.mjs:50 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/setup/doctor.mjs:97 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/setup/init.mjs:620 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/setup/doctor.mjs:88 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
npx invocation of non-well-known packagesrc/setup/wiring.mjs:75 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/setup/init.mjs:488 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/setup/doctor.mjs:84 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/client.mjs:177 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagesrc/setup/doctor.mjs:98 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim fjgbue: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim fjgbue